Method and device for detecting water shortage state of driver

Abstract

The invention relates to the technical field of intelligent cabins, in particular to a water shortage state detection method and device for a driver, and the method comprises the steps: collecting a plurality of driving behavior image frames of the driver; extracting at least one key feature of the driver from each driving behavior image frame; and acquiring the driving state of the vehicle corresponding to each driving behavior image frame, and identifying the actual water shortage state of the driver according to the driving state and the at least one key feature. Therefore, the problems that the water shortage state of the driver cannot be effectively monitored through face recognition or by means of an independent device in the prior art, a mechanism for effectively combining the vehicle driving state and the driver behavior lacks, privacy is prone to be invaded and the like are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cockpits, and in particular to a method and device for detecting a water shortage state of a driver. Background Art

[0002] In the modern driving environment, ensuring the health and alertness of drivers is essential to improving road safety. The driver's dehydration status can significantly affect their reaction time and judgment ability, so a system is needed to monitor and remind drivers about their hydration status in real time to reduce driving risks caused by dehydration.

[0003] Current driver monitoring systems mainly focus on behavior and vehicle operating status, and few systems can integrate the driver's physiological signals for real-time analysis and feedback. Existing general monitoring of the driver's dehydration status is mainly through face recognition or with the help of separate equipment, but these methods have shortcomings such as inability to effectively monitor the driver's dehydration status, lack of a mechanism to effectively combine the vehicle's driving status with the driver's behavior, and privacy infringement. For example:

[0004] (1) A vision-based in-cabin drinking status detection algorithm, which uses the upper limb key point detector to detect and judge the driver's status. If it is detected that the driver has left the steering wheel with one hand, the drinking detector is used to determine whether the driver is drinking water. If the driver is drinking water, it is determined whether there is a drinking container in the image; the drinking container is classified based on a fine classifier to determine whether it is an open container or a straw cup; if the drinking container is an open container, the driver's head pitch angle is determined based on facial key point detection to determine whether it affects the line of sight. This method relies on the perception of the driver's characteristics and is easily affected by the external environment. Facial perception can also cause privacy violations.

[0005] (2) Abnormal behavior detection method based on deep learning, such as drinking water. This method requires the use of transformer-based models such as Dlib and cannot be deployed on vehicle chips;

[0006] (3) A driving status monitoring method and device, which performs driver status detection on a driver image, outputs the driver's driving status monitoring result based on the driver status detection result, and performs intelligent driving control. However, there is also the problem of infringing the driver's privacy. Summary of the invention

[0007] The present invention provides a method and device for detecting a driver's water shortage status, so as to solve the problems that the existing method of detecting a driver's water shortage status by face recognition or with the help of a separate device cannot effectively monitor the driver's water shortage status, lacks a mechanism for effectively combining the vehicle driving status with the driver's behavior, and is prone to infringing privacy.

[0008] The first aspect of the present invention provides a method for detecting a driver's water shortage status, comprising the following steps: collecting multiple driving behavior image frames of the driver; extracting at least one key feature of the driver from each driving behavior image frame; acquiring the driving status of the vehicle corresponding to each driving behavior image frame, and identifying the actual water shortage status of the driver based on the driving status and the at least one key feature.

[0009] Optionally, extracting at least one key feature of the driver includes:

[0010] Identify the lip area in each driving behavior image frame; segment the tongue in the lip area to obtain a real lip area; determine at least one key point of the driver's lips in the real lip area as the at least one key feature.

[0011] Optionally, the identifying the actual water shortage state of the driver according to the driving state and the at least one key feature comprises:

[0012] Calculating a first expansion coefficient of the real lip area according to the driving state; acquiring a drinking action of the driver, and calculating a second expansion coefficient of the real lip area according to the drinking action;

[0013] The final expansion coefficient is calculated according to the expansion coefficient base, the first expansion coefficient, and the second expansion coefficient; and the driver's licking action is acquired according to the at least one key feature and the final expansion coefficient, so as to determine the actual water shortage state according to the licking action.

[0014] Optionally, it further includes: matching the driver's water shortage reminder action according to the actual water shortage state;

[0015] The vehicle is controlled to provide water shortage reminder based on the water shortage reminder action.

[0016] Optionally, matching the driver's water shortage reminder action according to the actual water shortage state includes:

[0017] Acquire the driver's reminder preference and / or driving habit; based on the reminder preference and / or the driving habit, match the driver's water shortage reminder action according to the actual water shortage status, wherein the water shortage reminder action includes at least one of reminder frequency, reminder method, and reminder intensity.

[0018] Optionally, it also includes:

[0019] Determine whether the actual water shortage state meets the preset rest condition; if the preset rest condition is met, remind the driver to take a rest, and when the reminder lasts longer than the preset time, plan a rest path for the vehicle, and control the vehicle to park along the rest path.

[0020] The second aspect of the present invention provides a device for detecting a driver's water shortage status, comprising: an acquisition module for acquiring multiple driving behavior image frames of the driver; an extraction module for extracting at least one key feature of the driver from each driving behavior image frame; and an identification module for acquiring the driving status of the vehicle corresponding to each driving behavior image frame, and identifying the actual water shortage status of the driver based on the driving status and the at least one key feature.

[0021] A third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for detecting a driver's water shortage status as described in the above embodiment.

[0022] A fourth aspect of the present invention provides a computer program product, which implements the above method for detecting the water shortage status of a driver when the computer program / instructions are executed by a processor.

[0023] A fifth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above method for detecting a water shortage status of a driver.

[0024] The method and device for detecting the dehydration status of a driver proposed in the embodiments of the present invention comprehensively consider the driver's lip licking behavior, the vehicle's driving status and the driver's drinking behavior to evaluate the driver's dehydration status in real time, thereby solving the problems that the existing methods of facial recognition or using separate equipment cannot effectively monitor the driver's dehydration status, lack a mechanism to effectively combine the vehicle's driving status with the driver's behavior, and are prone to privacy violations. It not only reduces the inattention or fatigue driving caused by dehydration and improves driving safety, but also provides personalized feedback, such as providing the driver with timely water replenishment reminders, and can adapt to the behaviors and needs of different drivers.

[0025] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 A flow chart of a method for detecting a driver's water shortage state provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the overall execution of the method for detecting a driver's water shortage state provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of tongue segmentation provided by an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of key points of lips provided in an embodiment of the present invention;

[0031] Figure 5 A schematic diagram of key point expansion and compression provided by an embodiment of the present invention;

[0032] Figure 6 A block diagram of a device for detecting a water shortage state of a driver provided by an embodiment of the present invention;

[0033] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0035] It should be noted that the embodiment of the present invention is based on the following key physiological and psychological behavioral principles, and uses lip licking as the principle basis for judging whether the driver is dehydrated.

[0036] (1) Dry mouth

[0037] When you are dehydrated, your body reduces the production of saliva to conserve water. Saliva plays a key role in keeping your mouth moist and aiding digestion. Reduced saliva makes your mouth feel dry. To temporarily relieve the dryness of your mouth and lips, people will instinctively lick their lips with their tongues, trying to increase the moisture on the surface of their lips in this way. This behavior is a natural reaction to cope with the discomfort caused by dryness.

[0038] (2) Behavioral feedback mechanism

[0039] Lip licking is a self-regulatory behavior that aims to relieve discomfort and restore a normal oral environment. Although this behavior cannot solve the underlying problem of dehydration, it provides an external observable signal of early warning of dehydration. Therefore, analyzing this behavior can also help understand the psychological and physiological state of the driver.

[0040] (3) Clinical observation and research

[0041] Multiple studies have shown that lip licking is one of the common early symptoms of dehydration. In clinical settings, doctors often ask patients whether they experience thirst or frequent lip licking to determine the degree of dehydration. Behavioral studies also support the view that lip licking is an indicator of dehydration, especially during long activities without immediate access to water.

[0042] Based on the above principles, it is scientific and effective to use lip licking as a behavioral standard for judging the driver's dehydration status. It provides a non-invasive monitoring method that can reflect the driver's physiological needs in real time, and is particularly suitable for use in activities such as driving where drinking water is not available at any time. By incorporating this behavior into the driver status monitoring system, driving safety can be improved, and drivers can be reminded to replenish water in time to avoid the decline in physical and cognitive functions caused by dehydration.

[0043] The following describes a method and device for detecting a driver's water shortage state according to an embodiment of the present invention with reference to the accompanying drawings.

[0044] Figure 1 A schematic flow chart of a method for detecting a driver's water shortage state provided by an embodiment of the present invention.

[0045] like Figure 1 As shown, the method for detecting the driver's water shortage state includes the following steps:

[0046] In step S101 , a plurality of driving behavior image frames of the driver are collected.

[0047] In the actual implementation process, a high-resolution camera is installed at an appropriate position inside the vehicle (usually the A-pillar or the steering wheel) to capture the upper body area of ​​the driver. The camera should be configured to continuously record the video stream, capture the possible behavior of the driver, and obtain the upper body behavior video; the upper body behavior video is framed to obtain multiple driving behavior image frames.

[0048] In step S102, at least one key feature of the driver is extracted from each driving behavior image frame.

[0049] In some embodiments, extracting at least one key feature of the driver includes:

[0050] Identify the lip region in each driving behavior image frame;

[0051] Segment the tongue in the lip area to obtain the real lip area;

[0052] At least one key point of the driver's lips in the real lip region is determined as at least one key feature.

[0053] In the actual implementation process, target detection algorithms such as yolov8 are used to detect the lip area in each driving behavior image frame, and the lip area is extracted using an image segmentation algorithm.

[0054] Furthermore, when licking lips, the tongue will always extend out and touch the lips, resulting in occlusion of the lip key points, but other areas may also occlude the lip key points. Therefore, the embodiment of the present invention needs to identify the tongue area to ensure that the key point occlusion is caused by the tongue to avoid misjudgment. Figure 3 As shown, that is, if a key point is invisible and is within the tongue segmentation area, it is determined to be blocked by the tongue.

[0055] Therefore, if Figure 2 As shown, after obtaining the lip area, the embodiment of the present invention determines whether there is a tongue in the lip area of ​​the current driving behavior image frame. If not, the lip area in the next driving behavior image frame is iteratively extracted until a tongue is present, and the tongue in the lip area is segmented using a semantic segmentation model to obtain a real lip area.

[0056] Furthermore, if Figure 4 As shown, the embodiment of the present invention uses a key point detection model such as HRNet to detect multiple key points in its real lip area as at least one key feature, and determines the initial position of each key point.

[0057] In step S103, the driving state of the vehicle corresponding to each driving behavior image frame is acquired, and the actual water shortage state of the driver is identified according to the driving state and at least one key feature.

[0058] In some embodiments, identifying the actual water shortage state of the driver according to the driving state and at least one key feature includes:

[0059] Calculating a first expansion coefficient of the actual lip region according to the driving state;

[0060] Acquire the driver's drinking action, and calculate the second expansion coefficient of the real lip area according to the drinking action;

[0061] Calculate the final expansion coefficient according to the expansion coefficient base, the first expansion coefficient, and the second expansion coefficient;

[0062] The driver's licking action is acquired according to at least one key feature and a final expansion coefficient to determine an actual water shortage state according to the licking action.

[0063] During the actual implementation process, the embodiment of the present invention also considers two other factors. One is the driving state of the vehicle. When turning, meeting other vehicles, etc., the driver is generally focused and will not lick his lips. If he licks his lips, it means that the possibility of the driver being dehydrated is increased. The second is that the driver drinks water. When it is detected that the driver has drunk water, it is unlikely that he will be dehydrated for a period of time thereafter.

[0064] Therefore, the embodiment of the present invention takes the initial positions of multiple key points in the real lip area as a reference, and then converts the vehicle driving state and drinking behavior into expansion coefficients, expanding or compressing the existing key point positions, thereby affecting the number and time of occluded key points.

[0065] Specifically, the initial positions of multiple key points in the real lip area are used as a reference, and a baseline expansion coefficient δ0 is set, which is the default value when there is no drinking behavior under normal driving conditions. For example, δ0 can be set to 0, indicating that the key point position remains unchanged when there is no additional influence.

[0066] The driving state of the vehicle corresponding to the current driving behavior image frame is obtained, and the baseline expansion coefficient is adjusted using the vehicle driving state to obtain the adjustment result δ of the vehicle driving state to the baseline expansion coefficient driver :

[0067] δ driver =δ0-k×f(status)

[0068] Among them, k is an adjustment coefficient that determines the degree of influence of the vehicle status on the expansion coefficient. f(status)=c1·|a|+c2·|θ| is a monitoring function constructed according to the vehicle's driving status, including the rate of change of vehicle speed a (acceleration) and the sharp change of steering angle θ, to evaluate the potential pressure or attention demand caused by the driving status to the driver. c1 and c2 are coefficients used to adjust the contribution weights of acceleration and steering angle to the expansion coefficient. These values ​​need to be adjusted according to actual conditions. a is the acceleration of the vehicle, indicating how fast the vehicle speed changes, and the unit can be m / s 2 , θ is the steering angle of the vehicle, indicating the sharpness of the turn. The unit can be degree (or radian). Converting it to degree can be more intuitive.

[0069] For example, in the case of emergency braking or sharp turns, the driver is focused on driving and is unlikely to lick his lips meaninglessly. If this happens, it means that the driver is indeed dehydrated, and the corresponding f(status) may return a higher positive value. Since k is a negative value, the overall expansion coefficient becomes smaller, the key points become more compact, and the tongue can cover more key points, reflecting a possible high risk of dehydration.

[0070] Furthermore, the driver's drinking behavior can be used to increase the expansion factor, thereby reflecting a lower risk of dehydration:

[0071] δ=δ water =δ driver +h×g(t)

[0072] Where δ is the final expansion coefficient, δ water is the adjustment result of the driver's drinking behavior on the baseline expansion coefficient, h is an adjustment coefficient that determines the degree to which the drinking behavior increases the expansion coefficient, and g(t) is a decay function that returns a value based on the time t since the last drinking, and gradually decreases with time. For example, an exponential decay model g(t) = e -λt , where λ is the decay rate, indicating the gradual decrease in the effect of drinking water over time.

[0073] Furthermore, the center point of multiple lip key points is the circle center P c , expand or compress the key points along the line connecting the center of the circle, according to the initial position P of each lip key point i Calculate the new position P i ′, the solution formula is as follows:

[0074] P i ′=P c +(P i -P c )×(1-δ)

[0075] like Figure 5 As shown, the red dot is the center point of the mouth. For each lip key point, its original position and the center point of the mouth are connected, and then the new position of the key point is calculated according to the above formula. When the position and shape of the tongue remain unchanged, the compression and expansion of the key point will affect the number of key points occluded by the tongue. Therefore, it is necessary to determine the number of key points occluded by the tongue in the current driving behavior image frame.

[0076] like Figure 2 As shown, after determining the number of key points of the current driving behavior image frame blocked by the tongue, the aforementioned extraction, segmentation and calculation behaviors are iteratively performed on the next driving behavior image frame, and the number of key points blocked by the tongue of the next driving behavior image frame is determined, until the cumulative number of key points blocked by the tongue within the preset time window exceeds the preset threshold, then it is determined that the driver frequently licks his lips and is in an actual dehydration state, wherein multiple preset thresholds can be set, and the number of occlusions is compared with the multiple preset thresholds respectively, so as to determine that the actual dehydration state is any one of the normal state, mild dehydration, moderate dehydration, severe dehydration, etc.

[0077] In some embodiments, it also includes:

[0078] Match the driver's water shortage reminder action according to the actual water shortage status;

[0079] The vehicle is controlled to provide water shortage reminder based on the water shortage reminder action.

[0080] During the actual implementation process, after determining the driver's actual water shortage status, the driver's reminder preferences and / or driving habits are obtained, and based on the reminder preferences and / or driving habits, the driver's water shortage reminder action is matched according to the actual water shortage status, wherein the water shortage reminder action includes at least one of the reminder frequency, reminder method, and reminder intensity, and the vehicle is controlled to provide water shortage reminder based on the water shortage reminder action.

[0081] In addition to reminding the driver to drink water, the embodiment of the present invention is also configured to determine whether the actual water shortage state meets the preset rest conditions. If the preset rest conditions are met, the driver is reminded to rest, and when the reminder lasts longer than the preset time, a rest path for the vehicle is planned, and the vehicle is controlled to stop along the rest path, so that the driver can get off the vehicle and engage in physical activities.

[0082] In summary, the method for detecting the driver's dehydration status proposed in an embodiment of the present invention comprehensively considers the driver's lip licking behavior, the vehicle's driving status and the driver's drinking behavior to evaluate the driver's dehydration status in real time, thereby solving the problems that the existing method of facial recognition or with the help of a separate device cannot effectively monitor the driver's dehydration status, lacks a mechanism to effectively combine the vehicle's driving status with the driver's behavior, and is prone to privacy infringement. It not only reduces the inattention or fatigue driving caused by dehydration and improves driving safety, but also provides personalized feedback, such as providing the driver with timely water replenishment reminders, which can adapt to the behaviors and needs of different drivers.

[0083] Next, the device for detecting the water shortage state of a driver according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0084] Figure 6 A block diagram of a device for detecting a driver's water shortage state provided by an embodiment of the present invention.

[0085] like Figure 6 As shown, the driver's water shortage state detection device 60 includes: a collection module 601, an extraction module 602 and a recognition module 603.

[0086] The acquisition module 601 is used to acquire multiple driving behavior image frames of the driver. The extraction module 602 is used to extract at least one key feature of the driver from each driving behavior image frame. The identification module 603 is used to obtain the driving state of the vehicle corresponding to each driving behavior image frame, and identify the actual water shortage state of the driver according to the driving state and at least one key feature.

[0087] In some embodiments, the extraction module 602 includes:

[0088] Identify the lip region in the current driving behavior image frame;

[0089] Segment the tongue in the lip area to obtain the real lip area;

[0090] At least one key point of the driver's lips in the real lip region is determined as at least one key feature.

[0091] In some embodiments, the identification module 603 includes:

[0092] Calculating a first expansion coefficient of the actual lip region according to the driving state;

[0093] Acquire the driver's drinking action, and calculate the second expansion coefficient of the real lip area according to the drinking action;

[0094] Calculate the final expansion coefficient according to the expansion coefficient base, the first expansion coefficient, and the second expansion coefficient;

[0095] The driver's licking action is acquired according to at least one key feature and a final expansion coefficient to determine an actual water shortage state according to the licking action.

[0096] In some embodiments, it also includes:

[0097] A matching module, used for matching the driver's water shortage reminder action according to the actual water shortage state;

[0098] The reminder module is used to control the vehicle to provide water shortage reminder based on the water shortage reminder action.

[0099] In some embodiments, matching the driver's water shortage reminder action according to the actual water shortage state includes:

[0100] Obtaining the driver's reminder preferences and / or driving habits;

[0101] Based on reminder preferences and / or driving habits, the driver's water shortage reminder action is matched according to the actual water shortage state, wherein the water shortage reminder action includes at least one of reminder frequency, reminder method, and reminder intensity.

[0102] In some embodiments, it also includes:

[0103] A judgment module, used to judge whether the actual water shortage state meets the preset rest conditions;

[0104] The control module is used to remind the driver to take a rest if the preset rest conditions are met, and when the reminder lasts longer than the preset time, plan a rest path for the vehicle and control the vehicle to stop along the rest path.

[0105] It should be noted that the above explanations of the embodiment of the method for detecting the water shortage status of a driver are also applicable to the device for detecting the water shortage status of a driver of this embodiment, and will not be repeated here.

[0106] The device for detecting the dehydration status of a driver proposed in an embodiment of the present invention comprehensively considers the driver's lip licking behavior, the vehicle's driving status and the driver's drinking behavior to evaluate the driver's dehydration status in real time, thereby solving the problems that the existing methods of facial recognition or using separate devices cannot effectively monitor the driver's dehydration status, lack a mechanism to effectively combine the vehicle's driving status with the driver's behavior, and are prone to privacy violations. It not only reduces the inattention or fatigue driving caused by dehydration and improves driving safety, but also provides personalized feedback, such as providing the driver with timely water replenishment reminders, and can adapt to the behaviors and needs of different drivers.

[0107] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of the present invention. The vehicle may include:

[0108] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0109] When the processor 702 executes the program, the method for detecting the water shortage state of the driver provided in the above embodiment is implemented.

[0110] Furthermore, the vehicle also includes:

[0111] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0112] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0113] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0114] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0115] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0116] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0117] An embodiment of the present invention further provides a computer program product, and when the computer program / instructions are executed by a processor, the above method for detecting a water shortage state of a driver is implemented.

[0118] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the above method for detecting a water shortage state of a driver is implemented.

[0119] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0120] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0121] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0122] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0123] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0124] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0125] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0126] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for detecting a driver's water shortage state, characterized in that: The following steps are involved: Collecting multiple driving behavior image frames of the driver; Extracting at least one key feature of the driver from each driving behavior image frame; as well as The driving state of the vehicle corresponding to each driving behavior image frame is acquired, and the actual water shortage state of the driver is identified according to the driving state and the at least one key feature.

2. The method for detecting a driver's water shortage state according to claim 1, characterized in that: The extracting at least one key feature of the driver comprises: Identifying a lip region in each driving behavior image frame; Segmenting the tongue in the lip region to obtain a real lip region; At least one key point of the driver's lips in the real lip area is determined as the at least one key feature.

3. The method for detecting a driver's water shortage state according to claim 2, characterized in that: The identifying the actual water shortage state of the driver according to the driving state and the at least one key feature comprises: Calculating a first expansion coefficient of the real lip area according to the driving state; acquiring a drinking action of the driver, and calculating a second expansion coefficient of the real lip area according to the drinking action; Calculate a final expansion coefficient according to the expansion coefficient base, the first expansion coefficient, and the second expansion coefficient; The driver's licking action is acquired according to the at least one key feature and the final expansion coefficient, so as to determine the actual water shortage state according to the licking action.

4. The method for detecting a driver's water shortage state according to claim 1, characterized in that: Also includes: matching a water shortage reminder action of the driver according to the actual water shortage state; The vehicle is controlled to provide water shortage reminder based on the water shortage reminder action.

5. The method for detecting a driver's water shortage state according to claim 4, characterized in that: The step of matching the driver's water shortage reminder action according to the actual water shortage state includes: obtaining reminder preferences and / or driving habits of the driver; Based on the reminder preference and / or the driving habit, the water shortage reminder action of the driver is matched according to the actual water shortage state, wherein the water shortage reminder action includes at least one of reminder frequency, reminder mode, and reminder intensity.

6. The method for detecting a driver's water shortage state according to claim 1, characterized in that: Also includes: Determining whether the actual water shortage state meets the preset rest condition; If the preset rest condition is met, the driver is reminded to take a rest, and when the reminder lasts longer than the preset time, a rest path for the vehicle is planned, and the vehicle is controlled to park along the rest path.

7. A driver's water shortage detection device, characterized in that: include: A collection module, used for collecting multiple driving behavior image frames of the driver; An extraction module, used for extracting at least one key feature of the driver from each driving behavior image frame; as well as The recognition module is used to obtain the driving state of the vehicle corresponding to each driving behavior image frame, and to recognize the actual water shortage state of the driver according to the driving state and the at least one key feature.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for detecting a water shortage state of a driver as described in any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program / instruction is executed by a processor, the method for detecting a driver's water shortage state as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for detecting a water shortage state of a driver as described in any one of claims 1 to 6.

Images